Kestrel 4B Coder needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.0 GB (Q2_K) to 8.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
Kestrel 4B Coder – compact coding and agent model
Kestrel 4B Coder is a 4.33 billion‑parameter Qwen3.5‑based model fine‑tuned for coding, reasoning, tools, and vision. It is designed for local deployment on constrained devices, offering practical code generation and tool‑assisted workflows.
Good at
- Coding and code generation
- Tool‑assisted reasoning
- Vision‑enabled tasks
Limits
- No vision support on all quant types
- Requires 8 k context for memory estimates
- License is apache‑2.0
Best for
- Local coding assistants
- Tool‑driven agent workflows
- Edge device code generation
Who it’s for. Developers and hobbyists who need a lightweight coding model that runs on personal hardware. The model is suitable for local inference with limited VRAM and for building responsive agents.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.6 GB | 6.2 GB | Fits | Get file → | |
| F16 | 8.7 GB | 10.3 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 2.78 GB, memory 4.4 GB). For 6 GB VRAM use Q3_K_L (file size 2.48 GB, memory 4.1 GB). For 4 GB VRAM use Q2_K (file size 1.96 GB, memory 3.6 GB).
What GPU do you need for Kestrel 4B Coder?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q3_K_M (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.2 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.7 GB file, about 10.3 GB in use).
Which Kestrel 4B Coder quant should you choose?
Q4_K_M is the usual starting point for Kestrel 4B Coder: it balances file size and quality well. Here it is a 2.8 GB file.
The Q8_0 file is 4.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 2.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kestrel 4B Coder
How much VRAM does Kestrel 4B Coder need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Kestrel 4B Coder on an 8 GB GPU?
Yes, with Q8_0: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kestrel 4B Coder GGUF?
It depends on the quant: Q2_K is 2.0 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.5 GB, IQ4_XS is 2.6 GB, Q4_K_S is 2.6 GB and 6 more.
What context length does Kestrel 4B Coder support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.
Where can I download Kestrel 4B Coder GGUF?
The files are on Hugging Face in the mradermacher/Kestrel-4B-Coder-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Kestrel 4B Coder use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Kestrel 4B Coder on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 4.4 GB of VRAM at 8 k context, which fits in 8 GB.
Does the model support vision tasks?
Yes, the model has vision capability, but it is not available on all quant types and may require additional resources.
What license applies to this model?
The model is released under the apache‑2.0 license.